QUANTITATIVE DIAGNOSIS ON MAGNETIC-RESONANCE IMAGES OF CHRONIC-LIVER-DISEASE USING NEURAL NETWORKS

Authors
YOSHINO S KOBAYASHI A YAHAGI T FUKUDA H EBARA M OHTO M
Citation
S. Yoshino et al., QUANTITATIVE DIAGNOSIS ON MAGNETIC-RESONANCE IMAGES OF CHRONIC-LIVER-DISEASE USING NEURAL NETWORKS, IEICE transactions on fundamentals of electronics, communications and computer science, E77A(11), 1994, pp. 1846-1850
Citations number
NO
Categorie Soggetti
Engineering, Eletrical & Electronic","Computer Science Hardware & Architecture","Computer Science Information Systems
Journal title
IEICE transactions on fundamentals of electronics, communications and computer science → ACNP
ISSN journal
09168508
Volume
E77A
Issue
11
Year of publication
1994
Pages
1846 - 1850
Database
ISI
SICI code
0916-8508(1994)E77A:11<1846:QDOMIO>2.0.ZU;2-H
Abstract
We have classified parenchymal echo patterns of cirrhotic liver into 3 types, according to the size of hypoechoic nodular lesions. We have b een studying an ultrasonic image diagnosis system using the three-laye r back-propagation neural network. In this paper, we will describe the applications of the neural network techniques for recognizing and cla ssifying chronic liver disease, which use the nodular lesions in the P roton density and T2-weighed magnetic resonance images on the gray lev el of the pixels in the region of interest.